R packages


The package Surrogate

In a clinical trial, it frequently occurs that the most credible endpoint to evaluate the effectiveness of a new therapy is difficult to measure. In such a situation, it can be an effective strategy to replace the true endpoint by a biomarker that is easier to measure and that allows for the prediction of the treatment effect on the true endpoint. 

Before a surrogate can replace the true endpoint in a clinical trial, it has to be formally evaluated. However, the statistical validation of a surrogate endpoint is a far from trivial endeavour that requires fitting complex statistical models. The package ‚Surrogate’ allows the user to evaluate the validity of a surrogate based on the meta-analytic, causal-inference, and information-theoretic frameworks. The package can be downloaded here: http://cran.r-project.org/web/packages/Surrogate/   

Bugs or suggestions for improvements can be reported by contacting me 

The library requires the R software package, which can be downloaded here: http://www.r-project.org 


The package EffectTreat

In personalized medicine, one wants to know, for a given patient and his or her outcome for a predictor (pre-treatment variable), how likely it is that a treatment will be more beneficial than an alternative treatment. This package allows for the quantification of the predictive causal association (i.e., the association between the predictor variable and the individual causal effect of the treatment) and related metrics. 

The package can be downloaded here: http://cran.r-project.org/web/packages/EffectTreat/index.html

Bugs or suggestions for improvements can be reported by contacting me

The library requires the R software package, which can be downloaded here: http://www.r-project.org 


The package CorrMixed

In clinical practice and research settings in medicine and the behavioral sciences, it is often of interest to quanify the correlation of a continuous endpoint that was repeatedly measured (e.g., test-retest correlations, ICC, etc.). This package allows for estimating these correlations based on mixed-effects models.  

The package can be downloaded here: http://cran.r-project.org/web/packages/CorrMixed/index.html

Bugs or suggestions for improvements can be reported by contacting me

The library requires the R software package, which can be downloaded here: http://www.r-project.org 

Last update: April 4th, 2020